Model: GELU Model: 3 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 481 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')
Text #0
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.3333. Min Act: -0.1700
Data Index: 630259 (C4 (Web Text))
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.2708. Min Act: -0.1700
Data Index: 1312770 (C4 (Web Text))
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.1770. Min Act: -0.1700
Data Index: 1060280 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.1770. Min Act: -0.1700
Data Index: 1231398 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.1145. Min Act: -0.1700
Data Index: 194320 (C4 (Web Text))
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.0832. Min Act: -0.1700
Data Index: 899668 (C4 (Web Text))
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.0520. Min Act: -0.1700
Data Index: 314705 (C4 (Web Text))
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.0207. Min Act: -0.1700
Data Index: 232473 (C4 (Web Text))
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.0520. Min Act: -0.1700
Data Index: 46869 (C4 (Web Text))
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.0207. Min Act: -0.1700
Data Index: 218865 (C4 (Web Text))
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.0207. Min Act: -0.1700
Data Index: 21089 (C4 (Web Text))
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.0207. Min Act: -0.1700
Data Index: 576231 (C4 (Web Text))
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3333. Min Range: -4.3333
Max Act: 4.0207. Min Act: -0.1700
Data Index: 1161091 (C4 (Web Text))
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3333. Min Range: -4.3333
Max Act: 3.9894. Min Act: -0.1700
Data Index: 977026 (C4 (Web Text))
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3333. Min Range: -4.3333
Max Act: 3.9894. Min Act: -0.1700
Data Index: 598179 (C4 (Web Text))
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3333. Min Range: -4.3333
Max Act: 3.9582. Min Act: -0.1700
Data Index: 1440929 (Python Code)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3333. Min Range: -4.3333
Max Act: 3.9582. Min Act: -0.1700
Data Index: 1567414 (Python Code)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3333. Min Range: -4.3333
Max Act: 3.9582. Min Act: -0.1700
Data Index: 1524907 (Python Code)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3333. Min Range: -4.3333
Max Act: 3.9582. Min Act: -0.1700
Data Index: 731760 (C4 (Web Text))
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3333. Min Range: -4.3333
Max Act: 3.9582. Min Act: -0.1700
Data Index: 276156 (C4 (Web Text))
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19